{"id":"https://openalex.org/W2105076537","doi":"https://doi.org/10.1109/isspa.2007.4555480","title":"Improving language models by using distant information","display_name":"Improving language models by using distant information","publication_year":2007,"publication_date":"2007-02-01","ids":{"openalex":"https://openalex.org/W2105076537","doi":"https://doi.org/10.1109/isspa.2007.4555480","mag":"2105076537"},"language":"en","primary_location":{"id":"doi:10.1109/isspa.2007.4555480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2007.4555480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 9th International Symposium on Signal Processing and Its Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00187084","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103222074","display_name":"Armelle Brun","orcid":"https://orcid.org/0000-0002-9876-6906"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"A. Brun","raw_affiliation_strings":["INRIA Lorraine, University of Nancy I, Vandoeuvre-les-Nancy, France","Univ. Nancy 2, Nancy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Lorraine, University of Nancy I, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I90183372"]},{"raw_affiliation_string":"Univ. Nancy 2, Nancy","institution_ids":["https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030296247","display_name":"David Langlois","orcid":"https://orcid.org/0000-0002-1608-3571"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"D. Langlois","raw_affiliation_strings":["INRIA Lorraine, University of Nancy I, Vandoeuvre-les-Nancy, France","IUFM of Lorraine, BP 239, 54506 Vandoeuvre-l\u00e9s-Nancy Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Lorraine, University of Nancy I, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I90183372"]},{"raw_affiliation_string":"IUFM of Lorraine, BP 239, 54506 Vandoeuvre-l\u00e9s-Nancy Cedex, France","institution_ids":["https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090778317","display_name":"Kamel Sma\u0131\u0308li","orcid":"https://orcid.org/0000-0002-4237-7303"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4405264304","display_name":"Universit\u00e9 Nancy-II","ror":"https://ror.org/01hdgn839","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405264304"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"K. Smaili","raw_affiliation_strings":["INRIA Lorraine, University of Nancy I, Vandoeuvre-les-Nancy, France","University Nancy 2, BP 239, 54506 Vandoeuvre-l\u00e9s-Nancy Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Lorraine, University of Nancy I, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I90183372"]},{"raw_affiliation_string":"University Nancy 2, BP 239, 54506 Vandoeuvre-l\u00e9s-Nancy Cedex, France","institution_ids":["https://openalex.org/I4405264304"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2226,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47525906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.9739950895309448},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.9684134721755981},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.9634062051773071},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.8892306685447693},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7764496803283691},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.7558461427688599},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5934396982192993},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5675556063652039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5546525716781616},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.540038526058197},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5209338068962097},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5155068039894104},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4802118241786957},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.45050907135009766},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.41627931594848633},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.19714558124542236},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12109386920928955},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.10229870676994324}],"concepts":[{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.9739950895309448},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9684134721755981},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9634062051773071},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8892306685447693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764496803283691},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.7558461427688599},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5934396982192993},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5675556063652039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546525716781616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.540038526058197},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5209338068962097},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5155068039894104},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4802118241786957},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.45050907135009766},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.41627931594848633},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.19714558124542236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12109386920928955},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.10229870676994324},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/isspa.2007.4555480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2007.4555480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 9th International Symposium on Signal Processing and Its Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.5318","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.5318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/18/70/84/PDF/ISSAP2007.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00187084v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00187084","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Symposium on Signal Processing and its Applications - ISSPA 2007, Feb 2007, Sharjah, United Arab Emirates","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00187084v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00187084","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Symposium on Signal Processing and its Applications - ISSPA 2007, Feb 2007, Sharjah, United Arab Emirates","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W45470783","https://openalex.org/W80223213","https://openalex.org/W120237368","https://openalex.org/W158414620","https://openalex.org/W193071483","https://openalex.org/W206923703","https://openalex.org/W1500873938","https://openalex.org/W1502984613","https://openalex.org/W1590952807","https://openalex.org/W1597533204","https://openalex.org/W2013196554","https://openalex.org/W2020749563","https://openalex.org/W2045346852","https://openalex.org/W2049633694","https://openalex.org/W3129711340","https://openalex.org/W6604923857","https://openalex.org/W6608449611","https://openalex.org/W6630257147","https://openalex.org/W6635726886","https://openalex.org/W6661981116"],"related_works":["https://openalex.org/W1903115690","https://openalex.org/W2041167939","https://openalex.org/W2223833155","https://openalex.org/W2940857995","https://openalex.org/W2020757772","https://openalex.org/W1602608327","https://openalex.org/W2250909759","https://openalex.org/W4327499987","https://openalex.org/W2056250865","https://openalex.org/W2105076537"],"abstract_inverted_index":{"This":[0],"study":[1,41],"examines":[2],"how":[3],"to":[4,21,142],"take":[5],"originally":[6],"advantage":[7],"from":[8,28],"distant":[9,46],"information":[10],"in":[11,67,110],"statistical":[12],"language":[13,94,135],"models.":[14,39,48,90],"We":[15],"show":[16],"that":[17],"it":[18],"is":[19,54,139],"possible":[20],"use":[22],"n-gram":[23,47,89],"models":[24,34,53,136],"considering":[25],"histories":[26],"different":[27],"those":[29],"used":[30,119],"during":[31],"training.":[32],"These":[33,81],"are":[35],"called":[36],"crossing":[37,133],"context":[38,134],"Our":[40],"deals":[42],"with":[43],"classical":[44],"and":[45,56],"A":[49,58],"mixture":[50,61,74,93],"of":[51,65,69,112,130],"four":[52],"proposed":[55,132],"evaluated.":[57],"bigram":[59],"linear":[60],"achieves":[62,106],"an":[63],"improvement":[64,109],"14%":[66],"terms":[68,111],"perplexity.":[70],"Moreover":[71],"the":[72,76,117,121,128,131],"trigram":[73,78],"outperforms":[75],"standard":[77,88],"by":[79],"5.6%.":[80],"improvements":[82],"have":[83],"been":[84,97],"obtained":[85],"without":[86],"complexifying":[87],"The":[91],"resulting":[92],"model":[95],"has":[96],"integrated":[98],"into":[99],"a":[100,107],"speech":[101],"recognition":[102],"system.":[103],"Its":[104],"evaluation":[105,123],"slight":[108],"word":[113],"error":[114],"rate":[115],"on":[116,137],"data":[118],"for":[120],"francophone":[122],"campaign":[124],"ESTER":[125],"[1].":[126],"Finally,":[127],"impact":[129],"performance":[138],"presented":[140],"according":[141],"various":[143],"speakers.":[144]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}